© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30767
    Prev
    Next
    INDEX
    Explanations

    punishing those

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sp
    0.53
     Obi
    0.49
     English
    0.48
     i
    0.48
    irem
    0.47
     several
    0.47
     various
    0.46
     sehen
    0.46
     r
    0.45
     Perfect
    0.45
    POSITIVE LOGITS
    hydrocèle
    0.49
    යක
    0.47
    ότερα
    0.46
    다
    0.46
    ınt
    0.45
    ະຍ
    0.45
     cationic
    0.44
    ному
    0.43
    etière
    0.43
    holomorphic
    0.43
    Activations Density 0.000%

    No Known Activations